In the new digital age, the pace and volume of growing transportation related data is exceeding o... more In the new digital age, the pace and volume of growing transportation related data is exceeding our ability to manage and analyze it. In this position paper, we present a data engine, Godzilla, to ingest real-time traffic data and support analytic and data mining over traffic data. Godzilla is a multi-cluster approach to handle large volumes of growing data, changing workloads and varying number of users. The data originates at multiple sources, and consists of multiple types. Meanwhile, the workloads belong to three camps, namely batch processing, interactive queries and graph analysis. Godzilla support multiple language abstractions from scripting to SQL-like language.
ABSTRACT Due to the time-varying nature of wireless networks, it is required to find robust optim... more ABSTRACT Due to the time-varying nature of wireless networks, it is required to find robust optimal methods to control the behavior and performance of such networks; however, this is a challenging task since robustness metrics and QoS-based (Quality of service) constraints in a wireless environment are typically highly non-linear and non-convex. This paper explores the possibility of using graph theoretic metrics to provide robustness in a wireless network at the presence of a set of QoS constraints. In particular, we are interested in robust planning of a wireless network for a given demand matrix while preserving end-to-end delay for input demands below a given threshold set. To this end, we show that the upper bound of end-to-end round trip time between two nodes of a network can be approximated by point-to-point network criticality (or resistance distance) of the network. We construct a convex optimization problem to provide a delay-guaranteed jointly optimal allocation of transmit powers and link flows. We show that the solution provides a robust behavior, i.e. it is insensitive to the environmental changes such as wireless link disruption, this is expected because network criticality is a robustness metric. Our framework can be applied to a wide range of SINR (Signal to Interference plus Noise Ratio) values.
One of the important properties of a reliable communication network is the robustness to the envi... more One of the important properties of a reliable communication network is the robustness to the environmental changes. This paper looks at the design of robust networks from a new perspective. A graph-theoretical metric, betweenness, in combination with network weight matrix is used to define a global quantity, network criticality, to characterize the robustness of a network. We show that network criticality is a monotone decreasing function of weight matrix. Furthermore, it is shown that network criticality is a strictly convex function of network weight matrix. This leads to a well-defined convex optimization problem to find the optimal weight matrix assignment to minimize network criticality.
This paper reports on a probabilistic method for traffic engineering (specifically routing and re... more This paper reports on a probabilistic method for traffic engineering (specifically routing and resource allocation) in backbone networks, where the transport is the main service and robustness to the unexpected changes in network parameters is required. We analyze the network using the probabilistic betweenness of the network nodes (or links). The theoretical results lead to the definition of "criticality" for
We begin by considering the grand challenge to design application platforms that will enable the ... more We begin by considering the grand challenge to design application platforms that will enable the smart city. We identify two fundamental research challenges: 1. Cross-infrastructure Management Systems to coordinate resource use in a city; 2. Services Platforms that promote collective and individual intelligence. Next we report research progress in the design of application platforms that can support the smart applications required in the smart city. In particular, we describe the SAVI (Smart Applications on Virtual Infrastructure) application platform testbed for research in smart applications and its design using software-defined infrastructure. We present the CVST (Connected Vehicles and Smart Transportation) Platform for Intelligent Transportation Services in the Greater Toronto area, which runs on the SAVI testbed. Its design provides the intelligence to enable smart management in smart cities. We end with a discussion of general principles for the design of smart infrastructures.
Ensuring the conformance of a service systems endto-end delay to service level agreement (SLA) co... more Ensuring the conformance of a service systems endto-end delay to service level agreement (SLA) constraints is a challenging task that requires statistical measures beyond the average delay. In this paper, we study the real-time prediction of the end-to-end delay distribution in systems with composite services such as service function chains. In order to have a general framework, we use queueing theory to model service systems, while also adopting a statistical learning approach to avoid the limitations of queueing-theoretic methods such as stationarity assumptions or other approximations that are often used to make the analysis mathematically tractable. Specifically, we use deep mixture density networks (MDN) to predict the end-to-end distribution of the delay given the network's state. As a result, our method is sufficiently general to be applied in different contexts and applications. Our evaluations show a good match between the learned distributions and the simulations, which suggest that the proposed method is a good candidate for providing probabilistic bounds on the end-to-end delay of more complex systems where simulations or theoretical methods are not applicable.
Ensuring quality of service (QoS) guarantees in service systems is a challenging task, particular... more Ensuring quality of service (QoS) guarantees in service systems is a challenging task, particularly when the system is composed of more fine-grained services, such as service function chains. An important QoS metric in service systems is the end-to-end delay, which becomes even more important in delay-sensitive applications, where the jobs must be completed within a time deadline. Admission control is one way of providing end-to-end delay guarantee, where the controller accepts a job only if it has a high probability of meeting the deadline. In this paper, we propose a reinforcement learning-based admission controller that guarantees a probabilistic upper-bound on the end-to-end delay of the service system, while minimizes the probability of unnecessary rejections. Our controller only uses the queue length information of the network and requires no knowledge about the network topology or system parameters. Since long-term performance metrics are of great importance in service systems, we take an average-reward reinforcement learning approach, which is well suited to infinite horizon problems. Our evaluations verify that the proposed RL-based admission controller is capable of providing probabilistic bounds on the end-to-end delay of the network, without using system model information. Index Terms-Admission control, queueing networks, reinforcement learning, delay-sensitive applications.
Graph theory provides a powerful set of metrics and conceptual ideas to model and investigate the... more Graph theory provides a powerful set of metrics and conceptual ideas to model and investigate the behavior of communication networks. Most graph-theoretical frameworks in the networking literature are based on undirected graph models, where a symmetric link weight is assigned to each link of the network. However, many communication networks must account for directionality of communication links. This paper reports on an effort to extend some of the existing results of symmetric graphs to asymmetric ones. In particular we are interested in the behavior of random-walk based algorithms in directed graphs and we find the average travel time of a random-walk as a function of an asymmetric Laplacian matrix, which is in turn a function of link weights.
Auto-scalability has become an evident feature for cloud software systems including but not limit... more Auto-scalability has become an evident feature for cloud software systems including but not limited to big data and IoT applications. Cloud application providers now are in full control over their applications' microservices and macroservices; virtual machines and containers can be provisioned or deprovisioned on demand at runtime. Elascale strives to adjust both micro/macro resources with respect to workload and changes in the internal state of the whole application stack. Elascale leverages Elasticsearch stack for collection, analysis and storage of performance metrics. Elascale then uses its default scaling engine to elastically adapt the managed application. Extendibility is guaranteed through provider, schema, plug-in and policy elements in the Elascale by which flexible scalability algorithms, including both reactive and proactive techniques, can be designed and implemented for various technologies, infrastructures and software stacks. In this paper, we present the architecture and initial implementation of Elascale; an instance will be leveraged to add auto-scalability to a generic IoT application. Due to zero dependency to the target software system, Elascale can be leveraged to provide auto-scalability and monitoring as-a-service for any type of cloud software system.
2012 International Conference on Computing, Networking and Communications (ICNC), 2012
ABSTRACT Network criticality measures the robustness of a network to changes in topology, traffic... more ABSTRACT Network criticality measures the robustness of a network to changes in topology, traffic demand, and faults. Recent research has shown that path selection according to network criticality metrics can lead to improved utilization and reduced blocking in mesh networks. In this paper we investigate the selection of survivable routes within the context of dynamic routing using weighted random-walk path criticality routing (WRW-PCR). To build backup paths for primary routes a shared backup path selection strategy is considered. Each link is characterized by its active bandwidth, backup bandwidth, and available capacity. The WRW-PCR algorithm is used to find paths with less sensitivity to traffic and topology changes. We present simulation results that demonstrate that path criticality routing results in much lower blocking than alternative routing algorithms.
Motivated by interest in providing more efficient services in customer service systems, we use st... more Motivated by interest in providing more efficient services in customer service systems, we use statistical learning methods and delay history information to predict the conditional distribution of the customers' waiting times in queueing systems. From the predicted distributions, descriptive statistics of the system such as the mean, variance and percentiles of the waiting times can be obtained, which can be used for delay announcements, SLA conformance and better system management. We model the conditional distributions by mixtures of Gaussians, parameters of which can be estimated using Mixture Density Networks. The evaluations show that exploiting more delay history information can result in much more accurate predictions under realistic time-varying arrival assumptions.
IEEE Intelligent Transportation Systems Magazine, 2015
Disturbances in roadway networks due to increases in demand or drops in network capacity can seve... more Disturbances in roadway networks due to increases in demand or drops in network capacity can severely degrade the performance of the system. The robustness of a roadway network to such disturbances has been investigated using a variety of methods leading to disparate robust network designs. This paper introduces a unifying framework for understanding and applying different robust network designs based on the context of traffic disturbances and design goals. It presents the objectives, requirements and examples of robust network design with long-term (planning) and shortterm (operation) goals. A sample case study is presented to assess a short-term robust network design using traffic assignment. The preliminary testing results compared to conventional User Equilibrium and System Optimal traffic assignment, demonstrate 20% and 10% travel time savings with demand increase and supply reduction, respectively.
In the new digital age, the pace and volume of growing transportation related data is exceeding o... more In the new digital age, the pace and volume of growing transportation related data is exceeding our ability to manage and analyze it. In this position paper, we present a data engine, Godzilla, to ingest real-time traffic data and support analytic and data mining over traffic data. Godzilla is a multi-cluster approach to handle large volumes of growing data, changing workloads and varying number of users. The data originates at multiple sources, and consists of multiple types. Meanwhile, the workloads belong to three camps, namely batch processing, interactive queries and graph analysis. Godzilla support multiple language abstractions from scripting to SQL-like language.
In the new digital age, the pace and volume of growing transportation related data is exceeding o... more In the new digital age, the pace and volume of growing transportation related data is exceeding our ability to manage and analyze it. In this position paper, we present a data engine, Godzilla, to ingest real-time traffic data and support analytic and data mining over traffic data. Godzilla is a multi-cluster approach to handle large volumes of growing data, changing workloads and varying number of users. The data originates at multiple sources, and consists of multiple types. Meanwhile, the workloads belong to three camps, namely batch processing, interactive queries and graph analysis. Godzilla support multiple language abstractions from scripting to SQL-like language.
ABSTRACT Due to the time-varying nature of wireless networks, it is required to find robust optim... more ABSTRACT Due to the time-varying nature of wireless networks, it is required to find robust optimal methods to control the behavior and performance of such networks; however, this is a challenging task since robustness metrics and QoS-based (Quality of service) constraints in a wireless environment are typically highly non-linear and non-convex. This paper explores the possibility of using graph theoretic metrics to provide robustness in a wireless network at the presence of a set of QoS constraints. In particular, we are interested in robust planning of a wireless network for a given demand matrix while preserving end-to-end delay for input demands below a given threshold set. To this end, we show that the upper bound of end-to-end round trip time between two nodes of a network can be approximated by point-to-point network criticality (or resistance distance) of the network. We construct a convex optimization problem to provide a delay-guaranteed jointly optimal allocation of transmit powers and link flows. We show that the solution provides a robust behavior, i.e. it is insensitive to the environmental changes such as wireless link disruption, this is expected because network criticality is a robustness metric. Our framework can be applied to a wide range of SINR (Signal to Interference plus Noise Ratio) values.
One of the important properties of a reliable communication network is the robustness to the envi... more One of the important properties of a reliable communication network is the robustness to the environmental changes. This paper looks at the design of robust networks from a new perspective. A graph-theoretical metric, betweenness, in combination with network weight matrix is used to define a global quantity, network criticality, to characterize the robustness of a network. We show that network criticality is a monotone decreasing function of weight matrix. Furthermore, it is shown that network criticality is a strictly convex function of network weight matrix. This leads to a well-defined convex optimization problem to find the optimal weight matrix assignment to minimize network criticality.
This paper reports on a probabilistic method for traffic engineering (specifically routing and re... more This paper reports on a probabilistic method for traffic engineering (specifically routing and resource allocation) in backbone networks, where the transport is the main service and robustness to the unexpected changes in network parameters is required. We analyze the network using the probabilistic betweenness of the network nodes (or links). The theoretical results lead to the definition of "criticality" for
We begin by considering the grand challenge to design application platforms that will enable the ... more We begin by considering the grand challenge to design application platforms that will enable the smart city. We identify two fundamental research challenges: 1. Cross-infrastructure Management Systems to coordinate resource use in a city; 2. Services Platforms that promote collective and individual intelligence. Next we report research progress in the design of application platforms that can support the smart applications required in the smart city. In particular, we describe the SAVI (Smart Applications on Virtual Infrastructure) application platform testbed for research in smart applications and its design using software-defined infrastructure. We present the CVST (Connected Vehicles and Smart Transportation) Platform for Intelligent Transportation Services in the Greater Toronto area, which runs on the SAVI testbed. Its design provides the intelligence to enable smart management in smart cities. We end with a discussion of general principles for the design of smart infrastructures.
Ensuring the conformance of a service systems endto-end delay to service level agreement (SLA) co... more Ensuring the conformance of a service systems endto-end delay to service level agreement (SLA) constraints is a challenging task that requires statistical measures beyond the average delay. In this paper, we study the real-time prediction of the end-to-end delay distribution in systems with composite services such as service function chains. In order to have a general framework, we use queueing theory to model service systems, while also adopting a statistical learning approach to avoid the limitations of queueing-theoretic methods such as stationarity assumptions or other approximations that are often used to make the analysis mathematically tractable. Specifically, we use deep mixture density networks (MDN) to predict the end-to-end distribution of the delay given the network's state. As a result, our method is sufficiently general to be applied in different contexts and applications. Our evaluations show a good match between the learned distributions and the simulations, which suggest that the proposed method is a good candidate for providing probabilistic bounds on the end-to-end delay of more complex systems where simulations or theoretical methods are not applicable.
Ensuring quality of service (QoS) guarantees in service systems is a challenging task, particular... more Ensuring quality of service (QoS) guarantees in service systems is a challenging task, particularly when the system is composed of more fine-grained services, such as service function chains. An important QoS metric in service systems is the end-to-end delay, which becomes even more important in delay-sensitive applications, where the jobs must be completed within a time deadline. Admission control is one way of providing end-to-end delay guarantee, where the controller accepts a job only if it has a high probability of meeting the deadline. In this paper, we propose a reinforcement learning-based admission controller that guarantees a probabilistic upper-bound on the end-to-end delay of the service system, while minimizes the probability of unnecessary rejections. Our controller only uses the queue length information of the network and requires no knowledge about the network topology or system parameters. Since long-term performance metrics are of great importance in service systems, we take an average-reward reinforcement learning approach, which is well suited to infinite horizon problems. Our evaluations verify that the proposed RL-based admission controller is capable of providing probabilistic bounds on the end-to-end delay of the network, without using system model information. Index Terms-Admission control, queueing networks, reinforcement learning, delay-sensitive applications.
Graph theory provides a powerful set of metrics and conceptual ideas to model and investigate the... more Graph theory provides a powerful set of metrics and conceptual ideas to model and investigate the behavior of communication networks. Most graph-theoretical frameworks in the networking literature are based on undirected graph models, where a symmetric link weight is assigned to each link of the network. However, many communication networks must account for directionality of communication links. This paper reports on an effort to extend some of the existing results of symmetric graphs to asymmetric ones. In particular we are interested in the behavior of random-walk based algorithms in directed graphs and we find the average travel time of a random-walk as a function of an asymmetric Laplacian matrix, which is in turn a function of link weights.
Auto-scalability has become an evident feature for cloud software systems including but not limit... more Auto-scalability has become an evident feature for cloud software systems including but not limited to big data and IoT applications. Cloud application providers now are in full control over their applications' microservices and macroservices; virtual machines and containers can be provisioned or deprovisioned on demand at runtime. Elascale strives to adjust both micro/macro resources with respect to workload and changes in the internal state of the whole application stack. Elascale leverages Elasticsearch stack for collection, analysis and storage of performance metrics. Elascale then uses its default scaling engine to elastically adapt the managed application. Extendibility is guaranteed through provider, schema, plug-in and policy elements in the Elascale by which flexible scalability algorithms, including both reactive and proactive techniques, can be designed and implemented for various technologies, infrastructures and software stacks. In this paper, we present the architecture and initial implementation of Elascale; an instance will be leveraged to add auto-scalability to a generic IoT application. Due to zero dependency to the target software system, Elascale can be leveraged to provide auto-scalability and monitoring as-a-service for any type of cloud software system.
2012 International Conference on Computing, Networking and Communications (ICNC), 2012
ABSTRACT Network criticality measures the robustness of a network to changes in topology, traffic... more ABSTRACT Network criticality measures the robustness of a network to changes in topology, traffic demand, and faults. Recent research has shown that path selection according to network criticality metrics can lead to improved utilization and reduced blocking in mesh networks. In this paper we investigate the selection of survivable routes within the context of dynamic routing using weighted random-walk path criticality routing (WRW-PCR). To build backup paths for primary routes a shared backup path selection strategy is considered. Each link is characterized by its active bandwidth, backup bandwidth, and available capacity. The WRW-PCR algorithm is used to find paths with less sensitivity to traffic and topology changes. We present simulation results that demonstrate that path criticality routing results in much lower blocking than alternative routing algorithms.
Motivated by interest in providing more efficient services in customer service systems, we use st... more Motivated by interest in providing more efficient services in customer service systems, we use statistical learning methods and delay history information to predict the conditional distribution of the customers' waiting times in queueing systems. From the predicted distributions, descriptive statistics of the system such as the mean, variance and percentiles of the waiting times can be obtained, which can be used for delay announcements, SLA conformance and better system management. We model the conditional distributions by mixtures of Gaussians, parameters of which can be estimated using Mixture Density Networks. The evaluations show that exploiting more delay history information can result in much more accurate predictions under realistic time-varying arrival assumptions.
IEEE Intelligent Transportation Systems Magazine, 2015
Disturbances in roadway networks due to increases in demand or drops in network capacity can seve... more Disturbances in roadway networks due to increases in demand or drops in network capacity can severely degrade the performance of the system. The robustness of a roadway network to such disturbances has been investigated using a variety of methods leading to disparate robust network designs. This paper introduces a unifying framework for understanding and applying different robust network designs based on the context of traffic disturbances and design goals. It presents the objectives, requirements and examples of robust network design with long-term (planning) and shortterm (operation) goals. A sample case study is presented to assess a short-term robust network design using traffic assignment. The preliminary testing results compared to conventional User Equilibrium and System Optimal traffic assignment, demonstrate 20% and 10% travel time savings with demand increase and supply reduction, respectively.
In the new digital age, the pace and volume of growing transportation related data is exceeding o... more In the new digital age, the pace and volume of growing transportation related data is exceeding our ability to manage and analyze it. In this position paper, we present a data engine, Godzilla, to ingest real-time traffic data and support analytic and data mining over traffic data. Godzilla is a multi-cluster approach to handle large volumes of growing data, changing workloads and varying number of users. The data originates at multiple sources, and consists of multiple types. Meanwhile, the workloads belong to three camps, namely batch processing, interactive queries and graph analysis. Godzilla support multiple language abstractions from scripting to SQL-like language.
Uploads
Papers by Ali Tizghadam